Skip to main content
Mallory
← Back to News
internet-facing-service-vulnerabilityendpoint-software-vulnerabilityidentity-authentication-vulnerability

Google Says PageBreak AI Agent Found More Than 500 XSS Vulnerabilities

Vulnerability Disclosure · 2 sources · Updated 21d ago · First seen Oct 31, 2026

Google Says PageBreak AI Agent Found More Than 500 XSS Vulnerabilities

Google reports that PageBreak, its Gemini-powered security agent, has discovered more than 500 cross-site scripting (XSS) vulnerabilities across its web applications since becoming fully operational in January. Findings reach product teams only after deterministic validators reproduce exploits against running applications, producing what Google describes as a near-zero false-positive rate. Security engineers write these validators, which operate outside the agent loop. The discovery total has not been independently validated, and incomplete validator coverage can leave vulnerabilities undetected. Google retains unverified candidates for further investigation and is integrating PageBreak with initiatives such as CodeMender to generate fixes automatically.

Google's published examples include three high-severity vulnerabilities: cache poisoning in apis.google.com, XSS in admin.google.com, and universal XSS in the Tag Assistant Extension. The cache-poisoning flaw excluded an attacker-controlled URL segment from cache keys, allowing malicious JavaScript to be served to geographically nearby users; Google reported no evidence of exploitation of that vulnerability. The administrative-console flaw let attackers obtain a valid signature for a malicious redirect through a separate authorization endpoint, bypassing cryptographic protection. The extension vulnerability chained inadequate external-origin validation, nonce disclosure through a simulated handshake, and unsafe script loading to execute attacker-controlled JavaScript in a debugged page. These findings illustrate PageBreak's ability to identify multi-step exploit paths, while its validation requirements remain a constraint on detection coverage.

Do you run this?See affected versions and whether adversaries are exploiting it.
Check your exposure
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

5 events
  1. Reported Oct 31, 202621d ago

    Google publishes paper reporting more than 500 PageBreak XSS discoveries

    Google reported that PageBreak had discovered more than 500 XSS vulnerabilities across its web applications since entering full operation. It attributed a near-zero false-positive rate to independent deterministic validators that reproduce exploits against running applications; the reported total had not been independently validated.

    Google Discloses PageBreak AI Security Agent That Found 500+ XSS Bugs - InfoQ
  2. Reported Oct 31, 202621d ago

    PageBreak enters full operation

    Google's Gemini-powered security agent PageBreak entered full operation in January; the source does not specify the year. The agent investigates potential vulnerabilities and requires deterministic exploit verification before reporting findings to product teams.

    Google Discloses PageBreak AI Security Agent That Found 500+ XSS Bugs - InfoQ
  3. Reported Sep 24, 20262mo ago

    Google discloses universal XSS in the Tag Assistant Extension

    PageBreak identified an exploit chain combining insufficient external-origin validation, nonce disclosure through a simulated handshake, and unsafe script loading. An attacker with XSS on a google.com subdomain could use the chain to execute attacker-controlled JavaScript in a debugged page.

    Google's PageBreak Project - Real-World Findings - Google Bug Hunters
  4. Reported Sep 24, 20262mo ago

    Google discloses signature-bypass XSS in admin.google.com

    PageBreak discovered that an authorization endpoint could generate a valid signature for a malicious javascript: redirect URI. Attackers could reuse that signature at a separate administrative-console endpoint to execute JavaScript despite its cryptographic protection.

    Google's PageBreak Project - Real-World Findings - Google Bug Hunters
  5. Reported Sep 24, 20262mo ago

    Google discloses PageBreak-discovered cache poisoning in apis.google.com

    Google detailed a high-severity flaw that allowed an attacker-controlled URL segment to inject JavaScript into responses and poison cache entries shared with legitimate requests. The impact was geographically localized, and Google reported finding no evidence of real-world exploitation.

    Google's PageBreak Project - Real-World Findings - Google Bug Hunters
Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.

Open in app →

Organizations

1 linked
Google
Do you run this?See whether adversaries are exploiting this yet, and where the affected versions run in your environment.
Check Your Exposure
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.